ECToNAS: Evolutionary Cross-Topology Neural Architecture Search

arXiv:2403.05123v1 Announce Type: new
Abstract: We present ECToNAS, a cost-efficient evolutionary cross-topology neural architecture search algorithm that does not require any pre-trained meta controllers. Our framework is able to select suitable network architectures for different tasks and hyperparameter settings, independently performing cross-topology optimisation where required. It is a hybrid approach that fuses training and topology optimisation together into one lightweight, resource-friendly process. We demonstrate the validity and power of this approach with six standard data sets (CIFAR-10, CIFAR-100, EuroSAT, Fashion …

abstract algorithm architecture architectures arxiv cost cs.cv cs.lg cs.ne framework hybrid hybrid approach hyperparameter meta network neural architecture search optimisation search tasks topology training type